"""统计样本用到的字体（东亚字体），决定字体替换表要覆盖哪些。"""
import collections, re, sys, zipfile, pathlib
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parent.parent))
from common import IDS, sample_file, sniff
tot = collections.Counter()
for sid in IDS:
    f = sample_file(sid)
    if sniff(f) != "docx":
        continue
    with zipfile.ZipFile(f) as z:
        xml = z.read("word/document.xml").decode("utf-8", "replace")
        sty = z.read("word/styles.xml").decode("utf-8", "replace") if "word/styles.xml" in z.namelist() else ""
    c = collections.Counter(re.findall(r'w:eastAsia="([^"]+)"', xml + sty))
    c.update(re.findall(r'w:ascii="([^"]+)"', xml + sty))
    tot.update(c)
    print(sid, c.most_common(6))
print("TOTAL", tot.most_common(15))